Author: Dann Corbit
Date: 19:58:36 12/17/99
Go up one level in this thread
On December 17, 1999 at 21:50:32, Vincent Diepeveen wrote:
[snip]
>Apart from this discussion great discussion about FPGA. You're however
>comparing with deep blue. I'm only interested in how much faster my program
>can get if i for example put my evaluation to FPGA.
How will the evaluation data get moved into the FPGA area? How will it come
back out again? How will the FPGA get at the hash tables? How will it
multiply, divide, add, subtract, and shift? It starts to sound a lot like a
general purpose CPU, doesn't it?
>What i'm doing in my evaluation is of course first adjust a bunch of
>variables and make lists with information to be processed later.
>
>Is this possible in FPGA, or does this require something that's hard
>to do in FPGA?
The USENET newsgroup news:comp.arch.fpga people could tell you about feasibility
for your design.
In fact, I just posted this message over there:
Subject: Dumb question springing from a discussion about chess on a chip...
There is a recent discussion on the computer chess club internet forum about the
feasibility of creating a chess chip using FPGA. Now, a chess chip *must* have
very fast access to large amounts of shared memory, and also be able to execute
an instruction set (much like a general purpose CPU -- but the instruction set
is {of course} specialized for chess).
My question:
Is it a good idea to attempt this with an FPGA, or should a general purpose CPU
be fabricated or should it be done with something else entirely?
This page took 0.01 seconds to execute
Last modified: Thu, 15 Apr 21 08:11:13 -0700
Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.